Victor Gallego
vicgalle
AI & ML interests
Preference fine-tuning, alignment & synthetic data.
Building LLMs in general!
Recent Activity
liked
a model
7 days ago
Qwen/Qwen2.5-Coder-32B-Instruct
liked
a dataset
12 days ago
lingjie23/TexAes
updated
a collection
25 days ago
Configurable Safety Tuning ⚙️
Organizations
vicgalle's activity
Adding the Open Portuguese LLM Leaderboard Evaluation Results
#4 opened about 2 months ago
by
leaderboard-pt-pr-bot
Datasets used
2
#1 opened 3 months ago
by
chaitanyamanem
Adding Evaluation Results
#2 opened 3 months ago
by
leaderboard-pr-bot
Link model to paper
#1 opened 4 months ago
by
nielsr
Link model to paper
#1 opened 4 months ago
by
nielsr
training detail?
2
#8 opened 4 months ago
by
max1321
Adding Evaluation Results
#3 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#2 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#5 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#3 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#3 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#3 opened 4 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#7 opened 5 months ago
by
leaderboard-pr-bot
Temperature for Benchmark
2
#3 opened 5 months ago
by
backendmagier
did the model train on multi turn conversation or single turn
1
#6 opened 5 months ago
by
duongnghia222
"observation" role in tokeniser
2
#11 opened 6 months ago
by
vicgalle
<|eot_id|><|start_header_id|>assistant<|end_header_id|> in model outputs
2
#5 opened 6 months ago
by
willsims
Base model
2
#2 opened 6 months ago
by
Stark2008
Adding Evaluation Results
#1 opened 6 months ago
by
leaderboard-pr-bot